© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    tapahtunut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kah
    -0.11
     kuv
    -0.11
    oux
    -0.10
     poh
    -0.10
     Kah
    -0.10
     vag
    -0.09
     prest
    -0.09
     prestige
    -0.09
    immel
    -0.09
    ater
    -0.09
    POSITIVE LOGITS
    ett
    0.13
     vast
    0.11
     tied
    0.11
     vir
    0.11
     ja
    0.11
    miss
    0.11
     penn
    0.10
    OTTOM
    0.10
    kin
    0.10
    ää
    0.10
    Activations Density 0.029%

    No Known Activations